A line fault determination system and method

Abstract

The application provides a line fault determination system and method, belongs to the field of line fault determination, solves the problem of low line fault determination efficiency, and specifically as follows: historical power consumption data is acquired, and expected power consumption is calculated; different voltage-power change models are defined according to the number of power supply ends and the number of municipal districts of a power transmission line, expected received power and expected received voltage are calculated in combination with the expected power consumption of each municipal district, and the expected received power and the expected received voltage are compared with actual received power and actual received voltage to determine the position of the fault; the position of the fault occurring on the power transmission line is fed back, a dual AI value keeper model is constructed, and the power transmission line is deployed and continuously monitored; the application acquires, processes and analyzes the relevant data of the power transmission line, defines the change law of the power and voltage of each transformer substation on the power transmission line, and improves the line fault checking efficiency.

Description

Technical Field

[0001] This invention relates to a line fault determination system and method, and pertains to the field of fault determination. Background Technology

[0002] Existing methods or systems for fault diagnosis of transmission lines have the following shortcomings:

[0003] Limited detection methods and indicators: Existing transmission line fault diagnosis systems mainly rely on electrical parameter measurement and signal analysis techniques to identify line anomalies. Currently, commonly used fault detection methods include impedance method, traveling wave method, and transient analysis method. However, these methods still face many challenges in terms of accuracy in practical applications. Impedance method is easily affected by changes in system operation mode, while the detection accuracy of traveling wave method is limited by the sensor installation location and signal attenuation.

[0004] Slow response speed: Existing fault detection methods for transmission lines often require tens of milliseconds or even longer from the occurrence of a fault to the output of the judgment result. This delay mainly comes from various stages of signal acquisition, transmission and processing. Especially in long-distance transmission lines, signal transmission delay and time synchronization problems between different monitoring points will further reduce the system's response speed.

[0005] Complex maintenance: Existing transmission line fault diagnosis systems require the deployment of a large number of high-precision sensors and reliable communication networks, which leads to high initial investment costs; in addition, the system installation process often requires power outages to facilitate the installation, which further increases indirect costs. Summary of the Invention

[0006] In view of the shortcomings of the existing technology, the purpose of this invention is to provide a line fault determination system and method, which aims to solve the problem of low efficiency in line fault determination.

[0007] To achieve the above objectives, the present invention provides a line fault determination system comprising:

[0008] Data acquisition module: used to obtain the number of municipal districts in the target area, obtain historical electricity consumption data for each municipal district; perform time-series analysis on the historical electricity consumption data, and calculate the expected electricity consumption for each municipal district;

[0009] Data Analysis Module: Used to count the number of power supply terminals, municipal districts, and substations corresponding to each transmission line; define different voltage-power change models based on the number of power supply terminals and municipal districts of each transmission line, and calculate the expected received power and expected received voltage of each substation on each transmission line in combination with the expected electricity consumption of each municipal district; obtain the actual received power and actual received voltage of each substation on each transmission line to determine the location of the fault on the transmission line;

[0010] Line fitting module: Used to provide feedback on the location of faults on transmission lines, build a dual AI duty officer model, and deploy it in the substation corresponding to each transmission line to continuously monitor the power and voltage changes on each transmission line.

[0011] Furthermore, the specific process for calculating the expected electricity consumption is as follows:

[0012] Obtain the hourly electricity consumption of the first municipal district; calculate the expected hourly electricity consumption.

[0013] The power consumption at each hour is differentially detected using ADF detection to obtain the differential order d.

[0014] The electricity consumption at each hour is subjected to d-order difference, and processed by autocorrelation function and partial autocorrelation function to obtain autoregressive parameter p and moving average parameter q;

[0015] Calculate the autocorrelation coefficient φ （1） ~φ （p） and the moving average coefficients θ of orders 1 to q （1） ~θ （q） ;

[0016] Let fe be the expected electricity consumption of the first urban district at time t on the next day. （t） Let the autoregressive coefficient of the lth order be φ. （l） Let the electricity consumption of the first municipal district at time t-l in the past day be he. （t－l） ;

[0017] Let the moving average coefficient of the s-th order be θ. （s） Let the electricity consumption of the first municipal district in the past day t-s be he. （t－s） he （t－s） The corresponding white noise is ε （t－s） ;

[0018] Construct formula A:

[0019] ;

[0020] Based on formula A, perform differential inverse operation to estimate the expected electricity consumption per hour for the first municipal district; calculate the expected electricity consumption for the second to mn-th municipal districts.

[0021] Furthermore, the specific procedures for defining different voltage-power change models are as follows:

[0022] Obtain the number of substations, power supply terminals, and municipal districts on the target line, and define different voltage-power change models based on the number of power supply terminals and municipal districts on the target line to determine whether a fault has occurred on the target line.

[0023] If the target line has only the first municipal district and one power supply end, then define voltage-power variation model A:

[0024] If there is only one power supply terminal on the target line, then count the number of parallel jurisdictions sr, and define voltage-power change model B:

[0025] If the target line has only the first municipal district but multiple power supply terminals, then the power supply terminals are considered as parallel districts, and the first municipal district is considered as a power supply terminal. The same process as defining voltage-power variation model B is repeated to define voltage-power variation model C:

[0026] Based on the voltage-power change model C, reverse power flow calculation is performed to determine the fault location of the target line and the 2nd to mnth corresponding transmission lines.

[0027] Furthermore, the specific process for defining voltage-power change model A is as follows:

[0028] Count the number of substations on the target line (ts+1);

[0029] Calculate the expected received power Po for the first municipal district. （1，0） ~Po （1,23） ;

[0030] Let Pe be the receiving power of the first substation. （1） The received voltage is Ue （1） The transmission power is Pi, and the transmission voltage is Ui;

[0031] Let the received power of the receiving substation be Po, and the received voltage be Uo;

[0032] Let the branch current be I. （1） I （4） and I （6） The main circuit current is I （2） I （3） I （5） and I （7） Let the equivalent impedances be Z and Z. （1） The equivalent admittance is Y （1） Y （2） and Y （3） ; where Y （1） and Y （2） The values ​​are equal;

[0033] Define formula A-1-1: ;

[0034] Formula A-1-2: ;

[0035] We obtain formula A-1-3 by combining the equations:

[0036] ;

[0037] Define formula A-2-1: ;

[0038] Formula A-2-2: ;

[0039] We obtain formula A-3 by combining the two equations:

[0040] ;

[0041] Define formula A-4-1: ;Formula A-4-2: ;

[0042] We obtain formula A-4-3 by combining the two equations: ;

[0043] Define formula A-5;

[0044] ;

[0045] We obtain formula A-6 by combining the two equations:

[0046] ;

[0047] Formulas A-3 and A-6 are used as voltage-power variation model A;

[0048] Obtain the rated operating voltage Uw of the receiving substation;

[0049] According to Uw and Po （1，0） Po （1，1） ~Po （1,23） Calculate the expected received power Pe of substations 1 to mn per hour. （1，0） ~Pe （tr,23） ; Expected received voltage Ue （1，0） ~Ue （tr,23） ; Expected transmission power Pi （1，0） ~Pi （tr,23） ;Desired transmission voltage Ui （1，0） ~Ui （tr,23） Define the criteria for determining line faults.

[0050] Furthermore, the specific process for defining the criteria for determining line faults is as follows:

[0051] Let fPe be the actual received power at time y of the x-th substation. （x，y） The actual received voltage is fUe （x，y） The actual transmission power is fPi （x，y） The actual transmission voltage is fUi（x，y） ;

[0052] Let Pe be the expected received power at time y of the x-th substation. （x，y） The expected received voltage is Ue （x，y） The expected transmission power is Pi （x，y） The expected transmission voltage is Ui （x，y） ;

[0053] Determine fPe （x，y） With Pe （x，y） Differences and fUe （x，y） With Ue （x，y） The difference is whether all of them are within ζ; ζ represents the determination coefficient.

[0054] If fPe （x，y） With Pe （x，y） Differences and fUe （x，y） With Ue （x，y） If the differences are all within ζ, then determine fPo （x，y） With Po （x，y） Differences and fUo （x，y） With Uo （x，y） Are all the differences within ζ?

[0055] If all values ​​are within ζ, then the substation is operating normally.

[0056] If it is not within ζ, then there is an anomaly downstream of the substation;

[0057] If fPe （x，y） With Pe （x，y） Differences and fUe （x，y） With Ue （x，y） If the difference is not within ζ, then determine whether formula A-7 is true;

[0058] Formula A-7:

[0059] ;

[0060] If formula A-7 holds true, then the upstream of the substation is abnormal, while the downstream is normal.

[0061] If formula A-7 holds true, then both the upstream and downstream of the substation are abnormal.

[0062] Obtain the actual received power, actual received voltage, actual transmitted power, and actual transmitted voltage of substations 1 to tr at each hour, and identify the fault area based on the judgment criteria.

[0063] Furthermore, the specific process for defining voltage-power change model B is as follows:

[0064] Get the transmission line length Li from the branch node to the first municipal district; get the transmission line length Lo from the branch node to the first to the srth parallel districts. （1） ~Lo （sr） ;

[0065] Obtain the current frequency fz on the target line, the conductor spacing Df, conductor radius Dr, relative permeability ur, conductor conductivity σ, air dielectric constant δr, and vacuum dielectric constant δo of the transmission cable;

[0066] Let Lo be the length of the transmission line from the branching node to the vth parallel jurisdiction. （v） The equivalent resistance Rxe of the vth parallel jurisdiction （v） ;

[0067] Define formula B-1:

[0068] ;

[0069] Calculate the equivalent resistance Rxe of the th to srth parallel jurisdictions. （1） ~Rxe （sr） ;

[0070] Let the equivalent inductance of the v parallel jurisdictions be Lxe （v） Define formula B-2:

[0071] ;

[0072] Calculate the equivalent inductance of the first to the srth parallel jurisdictions;

[0073] Let the equivalent impedance of the vth parallel jurisdiction be Zxe （v） Define formula B-3:

[0074] ;ij represents the imaginary unit; ω represents the angular frequency of the current. ;

[0075] Let the equivalent admittance of the vth parallel jurisdiction be Yxe. （v） Define formula B-4:

[0076] ;

[0077] Calculate the equivalent impedance of the first to the srth parallel jurisdictions.

[0078] Furthermore, the workflow for defining the voltage-power variation model B also includes:

[0079] Calculate the equivalent impedance Zx of the first municipal district based on Li;

[0080] Obtain the transmission line length Ll from the first municipal district to the first parallel municipal district. （o-1） The length Ll of the transmission line from the (sr-1)th parallel municipality to the srth parallel municipality. （（sr-1）-sr） ;

[0081] Calculate Ll （o-1） ~Ll （（sr-1）-sr） The corresponding equivalent impedance Zxl （o-1） ~Zxl （（sr-1）-sr） ;

[0082] Let the receiving power of the receiving substation corresponding to the first municipal district be Poo; let the receiving power of the receiving substation corresponding to the first to srth parallel districts be Pox. （1） ~Pox （sr） ;

[0083] Let the transmission power from the shunt node to the strain gauge power station be Ppx, and define formula B-5:

[0084] ;

[0085] Pox （v） This represents the receiving power of the receiving substation corresponding to the vth parallel jurisdiction;

[0086] Pox （n） This represents the receiving power of the receiving substation corresponding to the nth parallel jurisdiction;

[0087] Zxl （n-（n+1）） Let Qex represent the equivalent impedance from the nth parallel municipality to the (n+1)th parallel municipality; Qex represents the repeating term.

[0088] ;

[0089] Formula B-5 is used as voltage-power variation model B, and voltage-power variation model B is used as the basis for reverse power flow calculation in process B22 to determine the fault location of the target line.

[0090] Furthermore, the process for constructing the dual-mode AI duty officer model is as follows:

[0091] Obtain fault information for each transmission line corresponding to a substation or line, and generate a structured cluster of events as a sample set A;

[0092] The BERT+Transformer+MLP architecture is used as the framework for the dual AI duty officer model;

[0093] The sample set A is divided into a training set and a validation set in a 7:3 ratio. The default parameters of the dual AI duty officer model are optimized through supervised learning until the model can unbiasedly determine the cluster of items and the type of fault information.

[0094] Acquire misjudgment information for each transmission line corresponding to a substation or line; deploy two independent modes for work and training in the dual AI duty officer model; run in work mode when the model performs line fault inspection work; and run in training mode when the model is being trained.

[0095] The misjudged information is clustered and added to sample set A to obtain sample set B. Sample set A and sample set B are used alternately to train the AI ​​duty officer model a second time until the model outputs all misjudged information and the corresponding event clusters and fault types without bias, so as to realize the adaptive fault diagnosis function that does not rely on the rule base.

[0096] The dual AI duty officer model is deployed in the substation corresponding to each transmission line.

[0097] A method for determining line faults includes:

[0098] Obtain the number of municipal districts in the target area, and obtain historical electricity consumption data for each municipal district; perform time-series analysis on the historical electricity consumption data, and calculate the expected electricity consumption for each municipal district;

[0099] The number of power supply terminals, municipal districts, and substations corresponding to each transmission line is counted. Based on the number of power supply terminals and municipal districts of each transmission line, different voltage-power change models are defined. Combined with the expected electricity consumption of each municipal district, the expected received power and expected received voltage of each substation on each transmission line are calculated. The actual received power and actual received voltage of each substation on each transmission line are obtained to determine the location of the fault on the transmission line.

[0100] The system provides feedback on the location of faults on transmission lines, builds a dual-mode AI duty officer model, and deploys it in the substation corresponding to each transmission line to continuously monitor power and voltage changes on each transmission line.

[0101] Compared with the prior art, the beneficial effects of the present invention are:

[0102] Multi-model judgment: The data analysis module of this invention constructs multiple voltage-power change models for different power grid topologies. This invention can intelligently select the most suitable analysis model based on different combinations of the number of power supply terminals and the number of municipal districts, thus achieving highly accurate fault judgment and scenario adaptability.

[0103] Intelligent self-optimization feature: This invention adopts a BERT+Transformer+MLP architecture, combining supervised learning and continuous optimization mechanisms. The system generates structured event clusters from fault information as sample set A, and divides the training set and validation set in a 7:3 ratio. Through iterative optimization, it ensures that the model can judge various faults without bias. At the same time, this invention also collects manually corrected misjudgment information, which is clustered to form sample set B. By alternately using the two sets of samples for secondary training, the long-term applicability and maintenance convenience of the system are improved.

[0104] High accuracy: This invention integrates the advantages of both physical models and machine learning; the accurate modeling based on circuit theory ensures the reliability of the basic judgment, while the self-learning ability of the AI ​​algorithm continuously optimizes the judgment accuracy, enabling the system to adapt to various boundary conditions and special scenarios; making the system suitable for both large regional power grids and small dedicated networks. Attached Figure Description

[0105] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0106] Figure 1 This is a schematic diagram of the system of the present invention;

[0107] Figure 2 This is a schematic diagram of the method of the present invention;

[0108] Figure 3 This is a schematic diagram illustrating a one-to-one relationship in this invention;

[0109] Figure 4 This is a schematic diagram of a one-to-many relationship in this invention. Detailed Implementation

[0110] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0111] Example 1

[0112] Please see Figure 1 A line fault determination system includes:

[0113] Data acquisition module: used to obtain the number of municipal districts in the target area, obtain the historical electricity consumption data (yesterday) for each municipal district; perform time-series analysis on the historical electricity consumption data, and calculate the expected electricity consumption for each municipal district;

[0114] It should be noted that in this invention, "line" refers to a power transmission line; and "target area" refers to a city-level area where this invention (a line fault determination system and method) is used to determine line faults.

[0115] Process A: The workflow of the data acquisition module is as follows:

[0116] Obtain the number of municipal districts (mn) in the target region;

[0117] The electricity consumption data for the first municipal district was obtained from 0:00, 1:00, and up to 23:00 yesterday. （1,0） he （1,1） ~he （1,23） ;

[0118] to him （1,0） ~he （1,23） Perform time-series analysis to calculate the expected electricity consumption (qr) of the first municipal district from 0:00, 1:00, up to 23:00 on the next day. （1,0） ,qr （1,1） ~qr （1,23） ;

[0119] Using ADF detection, he was sequentially... （1,0） ~he （1,23） Perform differential detection to obtain the difference order d;

[0120] to him （1,0） ~he （1,23） Perform d-order differencing and process with the autocorrelation function (ACF) and partial autocorrelation function (PACF) to obtain the autoregressive parameter p and the moving average parameter q (the range of values ​​for d, p, and q are all [1, 24), and the values ​​of (24-p) and (24-q) are both greater than or equal to 1).

[0121] Calculate the autocorrelation coefficients φ for the 1st, 2nd, and up to the pth order. （1） φ （2） ~φ （p） and the moving average coefficients θ of orders 1 to q （1） θ （2） ~θ （q） ;

[0122] According to he （1,0） he （1,1） ~he （1,23） Calculate the autocorrelation coefficient φ （1，1） φ （1，2） ~φ （1，p） and the moving average coefficients θ of orders 1 to q （1，1） θ （1，2） ~θ （1，q） ;

[0123] Calculate he （1,0） ~he （1,23） The average value of ahe;

[0124] will {he （1,0） ~he（1,23）} as sequence H;

[0125] Calculate the differences from order 1 to p corresponding to sequence H to obtain sequence H. （1） ~H （p） ;

[0126] Calculate sequence H with respect to sequence H （1） ~H （p） The autocovariance is obtained by γ. （1） ~γ （p） ;

[0127] Construct a (1×p) matrix B （φ） : ;

[0128] Construct a (1×p) matrix B （1） : ;

[0129] Construct a (p×p) matrix B （2） : ; where matrix B （2） All elements on the diagonal are ahe; Rearrange sequence H with respect to sequence H （1） ~H （p-1） autocovariance γ （1） ~γ （p-1） symmetrically arranged in matrix B （2） Both sides of the diagonal;

[0130] Calculate φ （1，1） ~φ （1，p） Value: Where -1 represents the inverse of the matrix;

[0131] Compare the magnitudes of p and q, and calculate the moving average coefficients θ from the 1st to the qth order. （1） ~θ （q） ;

[0132] If p ≥ q, then according to sequence H with respect to sequence H （1） ~H （q） autocovariance to γ （1） ~γ （q） Construct a (1×q) matrix Bφ （q） : ;

[0133] Construct a (1×q) matrix B （θ） : ;

[0134] Construct a (q×q) matrix Bq: ; where the elements on the diagonal of matrix Bq are all sod; the sequence H is expressed about the sequence H （1） ~H（q-1） autocovariance γ （1） ~γ （q-1） symmetrically arranged in matrix B （2） Both sides of the diagonal;

[0135] Calculate θ （1） ~θ （q） Value: ;

[0136] If p < q, calculate the differences of order 1 to q of sequence H to obtain sequence Hq. （1） ~Hq （q） ;

[0137] Calculate sequence H with respect to sequence Hq （1） ~Hq （q） The autocovariance is obtained as γq. （1） ~γq （q） ;

[0138] Define the function ss(i):

[0139] ;wherein, γq （j） Represents sequence H with respect to sequence Hq （j） The autocovariance; θ （i） θ （j） and θ （j+i） , represent the moving average coefficients of the i-th, i-th and (j+i)-th orders respectively, where the values ​​of i and j are both in the range of 1 to (q-1).

[0140] Construct the matrix equation:

[0141] ; where θ （j+1） This represents the moving average coefficient of the (j+1)th order;

[0142] γq （1） ~γq （q） Substitute into the matrix equation and calculate θ （1） ~θ （q） The value;

[0143] Calculate he （1,0） he （1,1） ~he （1,23） The average value of Hhe;

[0144] Calculate he （1,0） ~he （1,23） White noise ε （0） ~ε （23） ; where ε （0） =he （1,0） -Hhe;ε （1） =he （1,1）-Hhe; and so on, ε （23） =he （1,23） -Hhe;

[0145] Let fe be the expected electricity consumption of the first urban district at time t on the next day. （t） Where t≤d;

[0146] Let the autoregressive coefficient of the lth order be φ. （l） Let the electricity consumption of the first urban district in the past day (t-l) be he. （t－l） Where, the value of l ranges from 1 to p;

[0147] Let the moving average coefficient of the s-th order be θ. （s） Let the electricity consumption of the first urban district in the past day (t-s) be he. （t－s） he （t－s） The corresponding white noise is ε （t－s） Where s takes values ​​from 1 to q; ε （t－s） ∈{ε （0） ~ε （23）};

[0148] Construct formula A:

[0149] ;

[0150] Based on formula A, perform differential inverse operation to predict the expected electricity consumption qr of the first municipal district at 0:00, 1:00, and up to 23:00 on the next day. （1，0） ,qr （1，1） ~qr （1,23） ;

[0151] Repeated calculation of qr （1，0） ~qr （1,23） Using the same steps, calculate the expected electricity consumption qr for the 2nd to mnth municipal districts. （2，0） ~qr （mn,23） .

[0152] Data Analysis Module: Used to count the number of power supply terminals, municipal districts, and substations corresponding to each transmission line; define different voltage-power variation models based on the number of power supply terminals (i.e., power plants or other municipal or provincial power grids) and municipal districts of each transmission line; and calculate the expected received power and expected received voltage of each substation on each transmission line by combining the expected electricity consumption of each municipal district; obtain the actual received power and actual received voltage of each substation on each transmission line to determine the location of the fault on the transmission line;

[0153] Process B: The specific process of the data analysis module is as follows:

[0154] Process B1: The transmission line supplying power to the first municipal district is designated as the target line;

[0155] Obtain the number of substations, power supply terminals, and municipal districts on the target line, and define different voltage-power change models based on the number of power supply terminals and municipal districts on the target line to determine whether a fault has occurred on the target line.

[0156] Process B2: Please refer to Figure 3 If the target line has only the first municipal district and one power supply end, i.e., a "one-to-one" relationship, then define voltage-power change model A:

[0157] The number of substations on the target line is counted (ts+1). The substation that directly supplies power to the first municipal district is taken as the receiving substation. Starting from the receiving substation, there are a total of ts substations on the target line.

[0158] Obtain the expected electricity consumption (qr) of the first municipal district from 0:00, 01:00, up to 23:00 on the next day. （1，0） ,qr （1，1） ~qr （1,23） ;

[0159] Calculate the expected received power Po of the receiving substation for the first municipal district from 0:00, 01:00, until 23:00 on the next day. （1，0） Po （1，1） ~Po （1,23） ;

[0160] Among them, Po （1，0） =qr （1，0） / (60×60); Po （1，1） =qr （1，1） / (60×60); and so on, Po （1，23） =qr （1，23） / (60×60);

[0161] Procedure B21: Let Pe be the receiving power of the first substation. （1） The received voltage is Ue （1） The transmission power is Pi, and the transmission voltage is Ui;

[0162] Let the received power of the receiving substation be Po, and the received voltage be Uo;

[0163] Let the branch current be I. （1） I （4） and I （6） The main circuit current is I （2） I （3） I （5） and I （7） Let the equivalent impedances be Z and Z. （1）The equivalent admittance is Y （1） Y （2） and Y （3） ; where Y （1） and Y （2） The values ​​are equal;

[0164] Define voltage-power variation model A:

[0165] According to Kirchhoff's current law, we know that:

[0166] (Formula A-1-1);

[0167] According to Ohm's law, we know that:

[0168] (Formula A-1-2);

[0169] Combining formulas A-1-1 and A-1-3, we obtain formula A-1-3:

[0170] (Formula A-1-3);

[0171] According to Joule's law, we know that:

[0172] (Formula A-2-1);

[0173] (Formula A-2-2);

[0174] Formula A-2-2 can be transformed to obtain:

[0175] (Formula A-2-3);

[0176] Substituting formulas A-1-3 and A-2-3 into formula A-2-2, we obtain formula A-2-4:

[0177] (Formula A-2-4);

[0178] Combining formulas A-1-1, A-1-2, and A-2-4, we obtain formula A-3:

[0179] (Derivation of Formula A-3);

[0180] From the derivation process of formula A-3, we can further obtain formula A-3:

[0181] (Formula A-3);

[0182] According to Kirchhoff's current law, we know that:

[0183] (Formula A-4-1);

[0184] According to Joule's law, we know that:

[0185] (Formula A-4-2);

[0186] Combining formulas A-1-2 and A-4-2, we obtain formula A-4-3:

[0187] (Formula A-4-3);

[0188] According to Ohm's law, we know that;

[0189] (Formula A-5-1);

[0190] Combining formulas A-4-2 and A-5-1, and transforming them, we get:

[0191] (Formula A-5-2);

[0192] Combining formulas A-4-3 and A-5-2, we obtain formula A-6:

[0193] (Formula A-6);

[0194] Formulas A-3 and A-6 are used as voltage-power variation model A;

[0195] Obtain the rated operating voltage of the receiving substation, denoted as Uw;

[0196] Process B22: Based on voltage-power change model A, with Uw as Uo and Po as... （1，0） Po （1，1） ~Po （1,23） Let Po be the expected received power Pe of the first substation in the first municipal district at 0:00, 01:00, and up to 23:00 on the next day. （1，0） Pe （1，1） ~Pe （1,23） ; Expected received voltage Ue （1，0） 、Ue （1，1） ~Ue （1,23） ; Expected transmission power Pi （1，0） Pi （1，1） ~Pi （1,23） ;Desired transmission voltage Ui （1，0） 、Ui （1，1） ~Ui （1,23） ;

[0197] The expected received power Pe of the second substation in the first municipal district at 0:00, 01:00, and up to 23:00 on the next day. （2，0） Pe （2，1） ~Pe （2,23） ; Expected received voltage Ue （2，0） 、Ue （2，1） ~Ue （2,23） ; Expected transmission power Pi （2，0） Pi （2，1） ~Pi （2,23） ;Desired transmission voltage Ui （2，0） 、Ui （2，1） ~Ui （2,23） ;

[0198] And so on, the expected received power Pe of the first municipal district at 0:00, 01:00, and up to 23:00 on the next day is calculated for the tr substation. （tr，0） Pe （tr，1） ~Pe （tr,23） ; Expected received voltage Ue （tr，0） 、Ue （tr，1） ~Ue （tr,23） ; Expected transmission power Pi （tr，0） Pi （tr，1） ~Pi （tr,23） ;Desired transmission voltage Ui （tr，0） 、Ui （tr，1） ~Ui （tr,23） ;

[0199] Define the criteria for determining line faults;

[0200] Procedure B221: Let fPe be the actual received power of the x-th substation at time y on the next day. （x，y） The actual received voltage is fUe （x，y） The actual transmission power is fPi （x，y） The actual transmission voltage is fUi （x，y） ;

[0201] Let Pe be the expected received power of the x-th substation at time y in the next day. （x，y） The expected received voltage is Ue （x，y） The expected transmission power is Pi （x，y） The expected transmission voltage is Ui （x，y） ;

[0202] Where x ranges from 1 to tr; and y ranges from 0 to 23.

[0203] Determine fPe （x，y） With Pe （x，y） The (numerical) differences and fUe （x，y） With Ue （x，y）The numerical differences are all within ζ; where ζ represents the determination coefficient; the value of ζ is 0.01; users or relevant technical personnel can adjust the value of ζ according to actual needs;

[0204] Process B222: If fPe （x，y） With Pe （x，y） The (numerical) differences and fUe （x，y） With Ue （x，y） If the (numerical) differences are all within ζ, then determine fPo. （x，y） With Po （x，y） The (numerical) differences and fUo （x，y） With Uo （x，y） Are the (numerical) differences all within ζ?

[0205] If fPo （x，y） With Po （x，y） The (numerical) differences and fUo （x，y） With Uo （x，y） If the (numerical) differences are all within ζ, it indicates that the x-th substation is normal;

[0206] If fPo （x，y） With Po （x，y） The (numerical) differences and fUo （x，y） With Uo （x，y） If the (numerical) difference is not within ζ, it indicates that an anomaly has occurred downstream of the xth substation.

[0207] Process B223: If fPe （x，y） With Pe （x，y） The (numerical) differences and fUe （x，y） With Ue （x，y） If the (numerical) difference is not within ζ, then determine whether formula A-7 is true;

[0208] Formula A-7:

[0209] ;

[0210] If formula A-7 holds true, it means that there is an anomaly upstream of the x-th substation, while the downstream is normal.

[0211] If formula A-7 holds true, it means that anomalies have occurred both upstream and downstream of the x-th substation.

[0212] Process B224: Based on the judgment conditions, obtain the actual received power, actual received voltage, actual transmitted power, and actual transmitted voltage of substations 1 to tr from 0:00 to 23:00 on the next day, and then sequentially compare them with their corresponding expected received power, expected received voltage, expected transmitted power, and expected transmitted voltage (i.e., Pe). （1，0） ~Pe（tr,23） Ue （1，0） ~Ue （tr,23） Pi （1，0） ~Pi （tr,23） and UI （1，0） ~Ui （tr,23） Compare and identify the faulty area;

[0213] Process B3: If there is only one power supply end on the target line, but multiple municipal districts, i.e., a "one-to-many" relationship, then define voltage-power change model B:

[0214] All other municipal districts along the target route, excluding the first municipal district, are considered as parallel districts; the number of parallel districts (sr) is counted.

[0215] Please see Figure 4 Define voltage-power variation model B;

[0216] Process B31: Obtain the transmission line length from the branch node to the first municipal district, and get Li; obtain the transmission line length from the branch node to the first, second, and up to the srth parallel districts, and get Lo. （1） Lo （2） ~Lo （sr） ;

[0217] Obtain the current frequency fz on the target line, the conductor spacing Df, conductor radius Dr, relative permeability ur, conductor conductivity σ, air dielectric constant δr, and vacuum dielectric constant δo of the (target line) transmission cable;

[0218] Let Lo be the length of the transmission line from the branching node to the vth parallel jurisdiction. （v） The equivalent resistance Rxe of the vth parallel jurisdiction （v） The value range of v is 1 to sr.

[0219] Define formula B-1:

[0220] ;

[0221] According to formula B-1, calculate the equivalent resistance Rxe of the 1st, 2nd, and up to the srth parallel jurisdictions. （1） Rxe （2） ~Rxe （sr） ;

[0222] Let the equivalent inductance of the v parallel jurisdictions be Lxe （v） Define formula B-2:

[0223] ;

[0224] According to formula B-1, calculate the equivalent inductance Lxe of the 1st, 2nd, up to the srth parallel jurisdiction. （1） Lxe （2） ~Lxe （sr） ;

[0225] Let the equivalent capacitance of the v parallel jurisdictions be Cxe （v） Define formula B-3:

[0226] ;

[0227] According to formula B-3, calculate the equivalent capacitance Cxe of the 1st, 2nd, up to the srth parallel jurisdiction. （1） Cxe （2） ~Cxe （sr） ;

[0228] Let the equivalent conductance of v parallel jurisdictions be Gxe （v） Define formula B-4:

[0229] ;

[0230] According to formula B-4, calculate the equivalent conductance Gxe of the 1st, 2nd, up to the srth parallel jurisdiction. （1） Gxe （2） ~Gxe （sr） ;

[0231] Let the equivalent impedance of the vth parallel jurisdiction be Zxe （v） Define formula B-5:

[0232] Where ij represents the imaginary unit; ω represents the angular frequency of the current. ;

[0233] Let the equivalent admittance of the vth parallel jurisdiction be Yxe. （v） Define formula B-6:

[0234] Where ij represents the imaginary unit;

[0235] Calculate the equivalent impedance Zxe of the 1st, 2nd, and up to the srth parallel jurisdictions according to formulas B-5 and B-6. （1） Zxe （2） ~Zxe （sr） Equivalent admittance Yxe （1） Yxe （2） ~Yxe （sr） ;

[0236] Lo in formulas B-1 to B-4 （v）Replace Li and calculate the equivalent resistance, equivalent inductance, equivalent capacitance, and equivalent susceptance of the first municipality; then, according to formulas B-5 to B-6, calculate the equivalent impedance Zx and equivalent admittance Yx of the first municipality.

[0237] Define the power flow formula corresponding to voltage-power variation model B, and obtain formula B-7;

[0238] Obtain the transmission line length Ll from the first municipal district to the first parallel municipal district. （o-1） The length Ll of the transmission line from the first parallel municipal district to the second parallel municipal district （1-2） The length Ll of the transmission line from the second parallel municipality to the third parallel municipality. （2-3） Similarly, the transmission line length Ll from the (sr-1)th parallel municipality to the srth parallel municipality is... （（sr-1）-sr） ;

[0239] Calculate Ll using formulas B-1 to B-6. （o-1） 、Ll （1-2） 、Ll （2-3） ~Ll （（sr-1）-sr） The corresponding equivalent impedance Zxl （o-1） Zxl （1-2） Zxl （2-3） ~Zxl （（sr-1）-sr） ;

[0240] Let the receiving power of the receiving substation corresponding to the first municipal district be Poo; and the receiving power of the receiving substation corresponding to the first, second, up to the srth parallel districts be Pox. （1） Pox （2） ~Pox （sr） ;

[0241] Let the transmission power from the shunt node to the strain gauge power station be Ppx, and define formula B-7:

[0242] ;

[0243] Pox （v） This represents the receiving power of the receiving substation corresponding to the v-th parallel jurisdiction.

[0244] Pox （n） This represents the receiving power of the receiving substation corresponding to the nth parallel jurisdiction, where the value of n ranges from 1 to (sr-1).

[0245] Zxl （n-（n+1）） This represents the equivalent impedance from the nth parallel municipality to the (n+1)th parallel municipality;

[0246] Qex represents the repeated term, and the formula for calculating Qex is:

[0247] ;

[0248] Formula B-7 is used as voltage-power variation model B, and voltage-power variation model B is used as process B22 to perform reverse power flow calculation and determine the fault location of the target line.

[0249] Process B4: If the target line has only the first municipal district but multiple power supply terminals (i.e., a "many-to-one" relationship), then treat the power supply terminals as parallel districts and the first municipal district as the power supply terminal, repeating the same process as in Process B3 for defining voltage-power change model B, and defining voltage-power change model C:

[0250] Reverse power flow calculations are performed based on the voltage-power change model C to determine the fault location of the target line;

[0251] Repeat the same process as for the first municipal district to determine whether the corresponding transmission line is faulty, and then determine whether the second to the mnth corresponding transmission lines are faulty.

[0252] Line fitting module: used to provide feedback on the location of faults on transmission lines and to build a dual "AI duty officer" model; the dual "AI duty officer" model is deployed in the substation corresponding to each transmission line and continuously monitors the power and voltage changes on each transmission line;

[0253] The process of constructing the dual-mode "AI duty officer" model is as follows:

[0254] Obtain fault information for each transmission line corresponding to a substation or line, and generate a structured cluster of events as a sample set A;

[0255] The BERT+Transformer+MLP architecture is used as the framework for the dual-mode "AI duty officer" model;

[0256] The sample set A is divided into a training set and a validation set in a 7:3 ratio. The default parameters of the dual-mode "AI duty officer" model (i.e. the default parameters in the BERT+Transformer+MLP architecture) are optimized through supervised learning until the "AI duty officer" model can unbiasedly determine the cluster of items corresponding to the fault information and the fault type.

[0257] Obtain misjudgment information for each transmission line corresponding to the substation or line (i.e., the erroneous fault information corrected by substation staff).

[0258] In the dual-mode "AI duty officer" model, two independent modes are deployed: "work" and "training". When the model performs line fault inspection, it runs in "work" mode; when the model is being trained, it runs in "training" mode.

[0259] The misjudged information is clustered and added to sample set A to obtain sample set B. Sample set A and sample set B are used alternately to train the "AI duty officer" model a second time until the model can output all misjudged information and the corresponding event clusters and fault types without bias, forming a closed-loop system of "signal acquisition - event cluster generation - intelligent judgment - feedback optimization" to achieve adaptive fault diagnosis function without relying on rule base.

[0260] The dual-mode "AI duty officer" model is deployed in the substation corresponding to each transmission line.

[0261] Example 2

[0262] Please see Figure 2 A method for determining line faults includes:

[0263] Step S1: Obtain the number of municipal districts in the target area, and obtain the historical electricity consumption data (yesterday) for each municipal district; perform time-series analysis on the historical electricity consumption data, and calculate the expected electricity consumption for each municipal district;

[0264] Step S2: Count the number of power supply terminals, the number of municipal districts, and the number of substations corresponding to each transmission line; define different voltage-power change models based on the number of power supply terminals and the number of municipal districts for each transmission line, and calculate the expected received power and expected received voltage for each substation on each transmission line in combination with the expected electricity consumption of each municipal district; obtain the actual received power and actual received voltage for each substation on each transmission line to determine the location of the fault on the transmission line;

[0265] Step S3: Feedback on the location of the fault on the transmission line and build a dual "AI duty officer" model; deploy the dual "AI duty officer" model in the substation corresponding to each transmission line and continuously monitor the power and voltage changes on each transmission line.

[0266] The above formulas are all dimensionless calculations. The formulas are derived from software simulations using a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation. For example, there are weighting coefficients and proportional coefficients. The values ​​set are to quantify each parameter to obtain a specific value, which is convenient for subsequent comparison. The values ​​of the weighting coefficients and proportional coefficients are only required to not affect the proportional relationship between the parameters and the quantified values.

[0267] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A line fault determination system, characterized in that, The system includes: Data acquisition module: used to obtain the number of municipal districts in the target area, obtain historical electricity consumption data for each municipal district; perform time-series analysis on the historical electricity consumption data, and calculate the expected electricity consumption for each municipal district; Data Analysis Module: Used to count the number of power supply terminals, municipal districts, and substations corresponding to each transmission line; define different voltage-power change models based on the number of power supply terminals and municipal districts of each transmission line, and calculate the expected received power and expected received voltage of each substation on each transmission line in combination with the expected electricity consumption of each municipal district; obtain the actual received power and actual received voltage of each substation on each transmission line to determine the location of the fault on the transmission line; The specific process for defining different voltage-power change models is as follows: Obtain the number of substations, power supply terminals, and municipal districts on the target line, and define different voltage-power change models based on the number of power supply terminals and municipal districts on the target line to determine whether a fault has occurred on the target line. If the target line has only the first municipal district and one power supply end, then define voltage-power variation model A: If there is only one power supply terminal on the target line, then count the number of parallel jurisdictions sr, and define voltage-power change model B: If the target line has only the first municipal district but multiple power supply terminals, then the power supply terminals are considered as parallel districts, and the first municipal district is considered as the power supply terminal. The same process as defining voltage-power variation model B is repeated to define voltage-power variation model C: Based on the voltage-power change model C, reverse power flow calculation is performed to determine the fault location of the target line and the 2nd to mnth corresponding transmission lines; Line fitting module: Used to provide feedback on the location of faults on transmission lines, build a dual AI duty officer model, and deploy it in the substation corresponding to each transmission line to continuously monitor the power and voltage changes on each transmission line.

2. The line fault determination system according to claim 1, characterized in that, The specific process for calculating expected electricity consumption is as follows: Obtain the hourly electricity consumption of the first municipal district; calculate the expected hourly electricity consumption. The power consumption at each hour is differentially detected using ADF detection to obtain the differential order d. The electricity consumption at each hour is subjected to d-order difference, and processed by autocorrelation function and partial autocorrelation function to obtain autoregressive parameter p and moving average parameter q; Calculate the autocorrelation coefficient φ （1） ~φ （p） and the moving average coefficients θ of orders 1 to q （1） ~θ （q） ; Let fe be the expected electricity consumption of the first urban district at time t on the next day. （t） Let the autoregressive coefficient of the lth order be φ. （l） Let the electricity consumption of the first municipal district at time t-l in the past day be he. （t－l） ; Let the moving average coefficient of the s-th order be θ. （s） Let the electricity consumption of the first municipal district in the past day t-s be he. （t－s） he （t－s） The corresponding white noise is ε （t－s） ; Construct formula A: ； Based on formula A, perform differential inverse operation to estimate the expected electricity consumption per hour for the first municipal district; calculate the expected electricity consumption for the second to mn-th municipal districts.

3. The line fault determination system according to claim 1, characterized in that, The specific process for defining voltage-power change model A is as follows: Count the number of substations on the target line (ts+1); Calculate the expected received power Po of the first municipal district. （1，0） ~Po （1,23） ; Let Pe be the receiving power of the first substation. （1） The received voltage is Ue （1） The transmission power is Pi, and the transmission voltage is Ui; Let the received power of the receiving substation be Po, and the received voltage be Uo; Let the branch current be I. （1） I （4） and I （6） The main circuit current is I （2） I （3） I （5） and I （7） Let the equivalent impedances be Z and Z. （1） The equivalent admittance is Y （1） Y （2） and Y （3） ; where Y （1） and Y （2） The values ​​are equal; Define formula A-1-1: ; Formula A-1-2: ; We obtain formula A-1-3 by combining the equations: ； Define formula A-2-1: ; Formula A-2-2: ; We obtain formula A-3 by combining the two equations: ； Define formula A-4-1: ;Formula A-4-2: ; We obtain formula A-4-3 by combining the two equations: ; Define formula A-5; ； We obtain formula A-6 by combining the two equations: ； Formulas A-3 and A-6 are used as voltage-power variation model A; Obtain the rated operating voltage Uw of the receiving substation; According to Uw and Po （1，0） Po （1，1） ~Po （1,23） Calculate the expected received power Pe of substations 1 to mn per hour. （1，0） ~Pe （tr,23） ; Expected received voltage Ue （1，0） ~Ue （tr,23） ; Expected transmission power Pi （1，0） ~Pi （tr,23） ;Desired transmission voltage Ui （1，0） ~Ui （tr,23） Define the criteria for determining line faults.

4. The line fault determination system according to claim 3, characterized in that, The specific process for defining the criteria for determining line faults is as follows: Let fPe be the actual received power at time y of the x-th substation. （x，y） The actual received voltage is fUe （x，y） The actual transmission power is fPi （x，y） The actual transmission voltage is fUi （x，y） ; Let Pe be the expected received power at time y of the x-th substation. （x，y） The expected received voltage is Ue （x，y） The expected transmission power is Pi （x，y） The expected transmission voltage is Ui （x，y） ; Determine fPe （x，y） With Pe （x，y） Differences and fUe （x，y） With Ue （x，y） The difference is whether all of them are within ζ; ζ represents the determination coefficient. If fPe （x，y） With Pe （x，y） Differences and fUe （x，y） With Ue （x，y） If the differences are all within ζ, then determine fPi. （x，y） With Pi （x，y） Differences and fUi （x，y） With UI （x，y） Are all the differences within ζ? If all values ​​are within ζ, then the substation is operating normally. If it is not within ζ, then there is an anomaly downstream of the substation; If fPe （x，y） With Pe （x，y） Differences and fUe （x，y） With Ue （x，y） If the difference is not within ζ, then determine whether formula A-7 is true; Formula A-7: ； If formula A-7 holds true, then the upstream of the substation is abnormal, while the downstream is normal. If formula A-7 does not hold true, then both the upstream and downstream of the substation are abnormal. Obtain the actual received power, actual received voltage, actual transmitted power, and actual transmitted voltage of substations 1 to tr at each hour, and identify the fault area based on the judgment criteria.

5. The line fault determination system according to claim 1, characterized in that, The specific process for defining voltage-power change model B is as follows: Get the transmission line length Li from the branch node to the first municipal district; get the transmission line length Lo from the branch node to the first to the srth parallel districts. （1） ~Lo （sr） ; Obtain the current frequency fz on the target line, the conductor spacing Df, conductor radius Dr, relative permeability ur, conductor conductivity σ, air dielectric constant δr, and vacuum dielectric constant δo of the transmission cable; Let Lo be the length of the transmission line from the branching node to the vth parallel jurisdiction. （v） The equivalent resistance Rxe of the vth parallel jurisdiction （v） ; Define formula B-1: ； Calculate the equivalent resistance Rxe of the 1st to srth parallel jurisdictions. （1） ~Rxe （sr） ; Let the equivalent inductance of the v parallel jurisdictions be Lxe （v） Define formula B-2: ； Calculate the equivalent inductance of the first to the srth parallel jurisdictions; Let the equivalent impedance of the vth parallel jurisdiction be Zxe （v） Define formula B-3: ;ij represents the imaginary unit; ω represents the angular frequency of the current. ; Let the equivalent admittance of the vth parallel jurisdiction be Yxe. （v） Define formula B-4: Among them, Gxe （v） This represents the equivalent conductance of the vth parallel jurisdiction; Calculate the equivalent impedance of the first to the srth parallel jurisdictions.

6. The line fault determination system according to claim 5, characterized in that, The workflow for defining voltage-power variation model B also includes: Calculate the equivalent impedance Zx of the first municipal district based on Li; Obtain the transmission line length Ll from the first municipal district to the first parallel municipal district. （o-1） The length Ll of the transmission line from the (sr-1)th parallel municipality to the srth parallel municipality. （（sr-1）-sr） ; Calculate Ll （o-1） ~Ll （（sr-1）-sr） The corresponding equivalent impedance Zxl （o-1） ~Zxl （（sr-1）-sr） ; Let the receiving power of the receiving substation corresponding to the first municipal district be Poo; let the receiving power of the receiving substation corresponding to the first to srth parallel districts be Pox. （1） ~Pox （sr） ; Let the transmission power from the shunt node to the strain gauge power station be Ppx, and define formula B-5: ； Pox （v） This represents the receiving power of the receiving substation corresponding to the vth parallel jurisdiction; Pox （n） This represents the receiving power of the receiving substation corresponding to the nth parallel jurisdiction; Zxl （n-（n+1）） Let Qex represent the equivalent impedance from the nth parallel municipality to the (n+1)th parallel municipality; Qex represents the repeating term. ； Formula B-5 is used as voltage-power variation model B, and voltage-power variation model B is used as the basis for reverse power flow calculation in process B22 to determine the fault location of the target line.

7. The line fault determination system according to claim 1, characterized in that, The process for building a dual-mode AI duty officer model is as follows: Obtain fault information for each transmission line corresponding to a substation or line, and generate a structured cluster of events as a sample set A; The BERT+Transformer+MLP architecture is used as the framework for the dual AI duty officer model; The sample set A is divided into a training set and a validation set in a 7:3 ratio. The default parameters of the dual AI duty officer model are optimized through supervised learning until the model can unbiasedly determine the cluster of items and the type of fault information. Acquire misjudgment information for each transmission line in response to substations or lines; deploy two independent modes for work and training in the dual AI duty officer model; When the model performs line fault detection, it runs in working mode; when training the model, it runs in training mode. The misjudged information is clustered and added to sample set A to obtain sample set B. Sample set A and sample set B are used alternately to train the AI ​​duty officer model a second time until the model outputs all misjudged information and the corresponding event clusters and fault types without bias, so as to realize the adaptive fault diagnosis function that does not rely on the rule base. The dual-mode AI duty officer model is deployed in the substation corresponding to each transmission line.

8. A method for determining line faults, applicable to the line fault determination system described in any one of claims 1-7, characterized in that, The determination method includes: Obtain the number of municipal districts in the target area, and obtain historical electricity consumption data for each municipal district; perform time-series analysis on the historical electricity consumption data, and calculate the expected electricity consumption for each municipal district; The number of power supply terminals, municipal districts, and substations corresponding to each transmission line is counted. Based on the number of power supply terminals and municipal districts of each transmission line, different voltage-power change models are defined. Combined with the expected electricity consumption of each municipal district, the expected received power and expected received voltage of each substation on each transmission line are calculated. The actual received power and actual received voltage of each substation on each transmission line are obtained to determine the location of the fault on the transmission line. The system provides feedback on the location of faults on transmission lines, builds a dual-mode AI duty officer model, and deploys it in the substation corresponding to each transmission line to continuously monitor power and voltage changes on each transmission line.

Images